restructure project

4 files changed, 295 insertions, 0 deletions

diff --git a/config/services/web/searx/default.nix b/config/services/web/searx/default.nix
new file mode 100644
index 0000000..7c5e593
--- /dev/null
+++ b/config/services/web/searx/default.nix
@@ -0,0 +1,32 @@
+{ config, lib, ... }:
+
+let
+  cfg = {
+    searx = config.services.searx;
+    filtron = config.services.filtron;
+  };
+in {
+  imports = [ ./searx ./filtron ./morty ];
+
+  services.nginx.virtualHosts."searx.aristote.fr" =
+    lib.mkIf (cfg.searx.enable && cfg.filtron.enable) {
+      locations = {
+        "/" = {
+          proxyPass = "http://${cfg.filtron.listen.address}:${
+              toString cfg.filtron.listen.port
+            }";
+          extraConfig = ''
+            proxy_set_header Host            $host;
+            proxy_set_header Connection      $http_connection;
+            proxy_set_header X-Real-IP       $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+            proxy_set_header X-Scheme        $scheme;
+            # proxy_set_header X-Script-Name   /;
+          '';
+        };
+        "/static".alias = "${pkgs.searx}/sjare/static";
+      };
+      forceSSL = true;
+      enableACME = true;
+    };
+}
diff --git a/config/services/web/searx/filtron/default.nix b/config/services/web/searx/filtron/default.nix
new file mode 100644
index 0000000..cc637c3
--- /dev/null
+++ b/config/services/web/searx/filtron/default.nix
@@ -0,0 +1,122 @@
+{ ... }:
+
+{
+  services.filtron = {
+    enable = true;
+    rules = [
+      {
+        name = "roboagent limit";
+        filters = [
+          "Header:User-Agent=(curl|cURL|Wget|python-requests|Scrapy|FeedFetcher|Go-http-client|Ruby|UniversalFeedParser)"
+        ];
+        limit = 0;
+        stop = true;
+        actions = [
+          { name = "log"; }
+          {
+            name = "block";
+            params = { message = "Rate limit exceeded"; };
+          }
+        ];
+      }
+      {
+        name = "botlimit";
+        filters = [
+          "Header:User-Agent=(Googlebot|bingbot|Baiduspider|yacybot|YandexMobileBot|YandexBot|Yahoo! Slurp|MJ12bot|AhrefsBot|archive.org_bot|msnbot|MJ12bot|SeznamBot|linkdexbot|Netvibes|SMTBot|zgrab|James BOT)"
+        ];
+        limit = 0;
+        stop = true;
+        actions = [
+          { name = "log"; }
+          {
+            name = "block";
+            params = { message = "Rate limit exceeded"; };
+          }
+        ];
+      }
+      {
+        name = "suspiciously frequent IP";
+        filters = [ ];
+        interval = 600;
+        limit = 30;
+        aggregations = [ "Header:X-Forwarded-For" ];
+        actions = [{ name = "log"; }];
+      }
+      {
+        name = "search request";
+        filters = [ "Param:q" "Path=^(/|/search)$" ];
+        interval = 61;
+        limit = 999;
+        subrules = [
+          {
+            name = "missing Accept-Language";
+            filters = [ "!Header:Accept-Language" ];
+            limit = 0;
+            stop = true;
+            actions = [
+              { name = "log"; }
+              {
+                name = "block";
+                params = { message = "Rate limit exceeded"; };
+              }
+            ];
+          }
+          # {
+          #   name = "suspiciously Connection=close header";
+          #   filters = [ "Header:Connection=close" ];
+          #   limit = 0;
+          #   stop = true;
+          #   actions = [
+          #     { name = "log"; }
+          #     {
+          #       name = "block";
+          #       params = { message = "Rate limit exceeded"; };
+          #     }
+          #   ];
+          # }
+          {
+            name = "IP limit";
+            interval = 61;
+            limit = 9;
+            stop = true;
+            aggregations = [ "Header:X-Forwarded-For" ];
+            actions = [
+              { name = "log"; }
+              {
+                name = "block";
+                params = { message = "Rate limit exceeded"; };
+              }
+            ];
+          }
+          {
+            name = "rss/json limit";
+            filters = [ "Param:format=(csv|json|rss)" ];
+            interval = 121;
+            limit = 2;
+            stop = true;
+            actions = [
+              { name = "log"; }
+              {
+                name = "block";
+                params = { message = "Rate limit exceeded"; };
+              }
+            ];
+          }
+          {
+            name = "useragent limit";
+            interval = 61;
+            limit = 199;
+            aggregations = [ "Header:User-Agent" ];
+            actions = [
+              { name = "log"; }
+              {
+                name = "block";
+                params = { message = "Rate limit exceeded"; };
+              }
+            ];
+          }
+        ];
+      }
+    ];
+  };
+}
diff --git a/config/services/web/searx/morty/default.nix b/config/services/web/searx/morty/default.nix
new file mode 100644
index 0000000..1a2b0e7
--- /dev/null
+++ b/config/services/web/searx/morty/default.nix
@@ -0,0 +1,22 @@
+{ config, lib, ... }:
+
+let cfg = config.services.morty;
+in {
+  services.nginx.virtualHosts."searx.aristote.fr".locations =
+    lib.mkIf cfg.enable {
+      "/morty/" = {
+        proxyPass = "http://127.0.0.1:${toString cfg.port}";
+        extraConfig = ''
+          proxy_set_header Host            $host;
+          proxy_set_header Connection      $http_connection;
+          proxy_set_header X-Real-IP       $remote_addr;
+          proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+          proxy_set_header X-Scheme        $scheme;
+        '';
+      };
+    };
+
+  services.morty = {
+    enable = false;
+  };
+}
diff --git a/config/services/web/searx/searx/default.nix b/config/services/web/searx/searx/default.nix
new file mode 100644
index 0000000..575b978
--- /dev/null
+++ b/config/services/web/searx/searx/default.nix
@@ -0,0 +1,119 @@
+{ config, lib, ... }:
+
+let
+  cfg = {
+    morty = config.services.morty;
+    filtron = config.services.filtron;
+  };
+in {
+  services.searx = {
+    enable = true;
+
+    runInUwsgi = true;
+    uwsgiConfig = {
+      cache2 = "name=searxcache,items=2000,blocks=2000,blocksize=4096,bitmap=1";
+      http = "$http://${cfg.filtron.target.address}:${toString cfg.filtron.target.port}";
+    };
+
+    environmentFile = /etc/searx/secrets;
+    settings = {
+      use_default_settings = true;
+      general = {
+        debug = false;
+        contact_url = "mailto:quentin@aristote.fr";
+        enable_stats = false;
+      };
+      search = {
+        autocomplete = "dbpedia";
+        default_lang = "fr-FR";
+      };
+      server = {
+        secret_key = "@SECRET_KEY@";
+        image_proxy = true;
+        http_protocol_version = "1.0";
+        method = "GET";
+      };
+      ui = { theme_args = { oscar_style = "pointhi"; }; };
+      result_proxy = lib.mkIf cfg.morty.enable {
+        url = "http://searx.aristote.fr/morty";
+        key = ''!!binary | "${keys.morty}"'';
+      };
+      enabled_plugins = [
+        "Open Access DOI rewrite"
+        "Hash plugin"
+        "HTTPS rewrite"
+        "Self Informations"
+        "Search on category select"
+        "Tracker URL remover"
+        "Vim-like hotkeys"
+      ];
+      engines = let
+        disable = names:
+          map (name: {
+            inherit name;
+            disabled = true;
+          }) names;
+      in (disable [
+        # general
+        "bing"
+        "currency"
+        "dictzone"
+        # files
+        "btdigg"
+        "torrentz"
+        # images
+        "bing images"
+        "ccengine"
+        "library of congress"
+        "qwant images"
+        # it
+        "hoogle"
+        # map
+        "photon"
+      ]) ++ [
+        {
+          name = "emojipedia";
+          engine = "xpath";
+          search_url = "https://emojipedia.org/search/?q={query}";
+          url_xpath = ''//ol[@class="search-results"]/li/h2/a/@href'';
+          title_xpath = ''//ol[@class="search-results"]/li/h2/a'';
+          content_xpath = ''//ol[@class="search-results"]/li/p'';
+          shortcut = "emoji";
+          disabled = true;
+          about = {
+            website = "https://emojipedia.org/";
+            wikidata_id = "Q22908129";
+            official_api_documentation = "";
+            use_official_api = false;
+            require_api_key = false;
+            results = "HTML";
+          };
+        }
+        {
+          name = "alternativeTo";
+          engine = "xpath";
+          paging = true;
+          search_url =
+            "https://alternativeto.net/browse/search?q={query}&p={pageno}";
+          results_xpath = ''
+            //article[@class="row app-list-item"]/div[@class="col-xs-10 col-sm-10 col-md-11 col-lg-offset-1 col-lg-11"]'';
+          url_xpath = "./h3/a/@href";
+          title_xpath = "./h3/a";
+          content_xpath =
+            ''./div[@class="itemDesc read-more-box"]/p[@class="text"]'';
+          shortcut = "a2";
+          categories = "it";
+          disabled = true;
+          about = {
+            website = "https://alternativeto.net";
+            wikidata_id = "Q3613175";
+            official_api_documentation = "";
+            use_official_api = false;
+            require_api_key = false;
+            results = "HTML";
+          };
+        }
+      ];
+    };
+  };
+}